Echo Agent is a self-hosted, long-running AI agent that connects language models, tools, memory, permissions, and messaging channels in one system. Individuals and teams use it for private automation that retains context across sessions, develops skills, schedules tasks, and requires approval for high-risk actions.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fuyuxiang/echo-agent --skill code-runnergit clone --depth 1 https://github.com/fuyuxiang/echo-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fuyuxiang/echo-agent/code-runner)<a href="https://agentmods.dev/skills/fuyuxiang/echo-agent/code-runner"><img src="https://agentmods.dev/badge/skills/fuyuxiang/echo-agent/code-runner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fuyuxiang/echo-agent/code-runner"><img src="https://agentmods.dev/badge/skills/fuyuxiang/echo-agent/code-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00561 |
| Opus 5.5 | $0.00010 | $0.00224 |
| Sonnet 5.5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
code-runner scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Blocked patterns**: `os.system`, `subprocess`, `shutil.rmtree`, `__import__('os')` What it actually says
Code Runner
Python code execution with resource limits and import restrictions; this is not an isolation boundary.
Usage
python3 scripts/safe_exec.py "print(sum(range(100)))"
python3 scripts/safe_exec.py --file script.py
python3 scripts/safe_exec.py --timeout 10 "import time; time.sleep(5); print('done')"
Security
Best-effort guards (NOT a true sandbox — code can still read the filesystem):
- Timeout: default 30 seconds, configurable
- Memory limit: 256MB on Linux (via resource.setrlimit); not enforced on macOS
- Blocked patterns:
os.system,subprocess,shutil.rmtree,__import__('os') - AST check: scans code for dangerous import patterns before execution
- Isolated working dir: runs in a fresh tmpdir, cleaned up after execution
- Minimal env: only PATH/HOME/LANG passed to subprocess
Limitations: This is NOT a security sandbox. The child process can read arbitrary files on the host filesystem. For untrusted code, use a container-based executor (e.g., docker-manage skill) instead.
Allowed Libraries
Safe for use (common data/analysis):
math,statistics,decimal,fractionsjson,csv,re,datetime,collectionspandas,numpy(if installed)matplotlib(saves to file, no display)
Blocked Patterns
BLOCKED = [
"os.system", "os.exec", "os.popen", "os.remove",
"subprocess", "shutil.rmtree", "importlib",
"__import__", "eval(", "exec(",
"open('/etc", "open('/root",
]
Example Workflows
Data analysis:
import pandas as pd
df = pd.read_csv("/tmp/data.csv")
print(df.describe())
print(df.groupby("category")["amount"].sum())
Quick plot (saved to file):
import matplotlib.pyplot as plt
plt.plot([1,2,3,4], [1,4,2,3])
plt.savefig("/tmp/plot.png")
print("Plot saved to /tmp/plot.png")
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 15d ago Changed · +1 tokens per session ba29b4d03b3e
- 1mo ago First seen · 72 lines · 24 tokens per session scan A cb8434dbdf69
code-runner is a skill published in the GitHub repository fuyuxiang/echo-agent (1,058 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 561 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.